English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Researchers have compared machine learning (ML) classifiers and discretechoice models (DCMs) in predicting travel behavior, but the generalizability ofthe findings is limited by the specifics of data, contexts, and authors'expertise. This study seeks to provide a generalizable empirical benchmark bycomparing hundreds of ML and DCM classifiers in a highly structured manner. Theexperiments evaluate both prediction accuracy and computational cost byspanning four hyper-dimensions, including 105 ML and DCM classifiers from 12model families, 3 datasets, 3 sample sizes, and 3 outputs. This experimentaldesign leads to an immense number of 6,970 experiments, which are corroboratedwith a meta dataset of 136 experiment points from 35 previous studies. Thisstudy is hitherto the most comprehensive and almost exhaustive comparison ofthe classifiers for travel behavioral prediction. We found that the ensemblemethods and deep neural networks achieve the highest predictive performance,but at a relatively high computational cost. Random forests are the mostcomputationally efficient, balancing between prediction and computation. Whilediscrete choice models offer accuracy with only 3-4 percentage points lowerthan the top ML classifiers, they have much longer computational time andbecome computationally impossible with large sample size, high inputdimensions, or simulation-based estimation. The relative ranking of the ML andDCM classifiers is highly stable, while the absolute values of the predictionaccuracy and computational time have large variations. Overall, this papersuggests using deep neural networks, model ensembles, and random forests asbaseline models for future travel behavior prediction. For choice modeling, theDCM community should switch more attention from fitting models to improvingcomputational efficiency, so that the DCMs can be widely adopted in the bigdata context.

Comparing hundreds of machine learning classifiers and discrete choice models in predicting travel behavior: an empirical benchmark